© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 378
    Prev
    Next
    INDEX
    Explanations

    the word "shoes"

    oai_token-act-pair · gpt-3.5-turbo

    references to shoes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erest
    -0.73
    itative
    -0.72
     subp
    -0.69
    PsyNetMessage
    -0.68
    arios
    -0.66
    VD
    -0.65
    itement
    -0.64
     Democr
    -0.63
    76561
    -0.63
    REDACTED
    -0.62
    POSITIVE LOGITS
    horn
    1.10
     shoes
    1.10
     Shoes
    0.99
    bridge
    0.97
    pee
    0.94
    prints
    0.89
    toe
    0.87
    mens
    0.86
     socks
    0.85
    ets
    0.84
    Activations Density 0.013%

    No Known Activations